Fluorescence-based detection of problematic cellular entities

Abstract

Techniques are for detecting presence of a problematic cellular entity in a target. In an example, using an analysis model, a fluorescence-based image is analyzed. The analysis model is trained using a number of reference fluorescence-based images for detecting the presence of problematic cellular entities in targets. Based on the analysis, a problematic cellular entity present in the target is detected. To perform the detection, the analysis model is trained to differentiate between the fluorescence in the fluorescence-based image emerging from the problematic cellular entity and the fluorescence in the fluorescence-based image emerging from regions other than the problematic cellular entity.

What is claimed is: 
     
       1. A device for examining a target, the device comprising:
 a first light source for emitting light for illuminating the target that causes a marker in the target to fluoresce, 
 a second light source for emitting light for illuminating the target without causing the marker in the target to fluoresce; 
 an image sensor configured to directly receive light emitted by the target in response to the illumination thereof by the first light source and by the second light source without an optical bandpass filter being disposed between the image sensor and the target, and to capture a plurality of images formed based on the light emitted; and 
 a processor configured to: 
 analyze, using an analysis model, a first image of the captured plurality of images, wherein the first image is a fluorescence-based image comprising fluorescence emerging from the target; 
 analyze, using the analysis model, a second image of the captured plurality of images to identify oxygenation at a plurality of regions of the target; and 
 detect, using the analysis model, presence of a problematic cellular entity in the target based on the analysis of the first image and based on the identified oxygenation at the plurality of regions of the target, wherein the analysis model is trained for detecting the presence of problematic cellular entities in targets, wherein the analysis model is trained using a plurality of reference fluorescence-based images for detecting the presence of problematic cellular entities in targets and wherein the analysis model is trained to differentiate between fluorescence in the fluorescence-based image emerging from the problematic cellular entity and fluorescence in fluorescence-based image emerging from regions of other than the problematic cellular entity. 
 
     
     
       2. The device of  claim 1 , comprising a smartphone, wherein the smartphone comprises:
 the processor; and 
 the image sensor. 
 
     
     
       3. The device of  claim 1 , wherein the processor is configured to:
 activate the first light source for emitting light onto the target; 
 activate the second light source for emitting light onto the target; and 
 activate the image sensor to capture light emitted by the target in response to illumination of the target by the first light source and to capture light emitted by the target in response to illumination of the target by the second light source. 
 
     
     
       4. The device of  claim 1 , wherein the target is a tissue or a tissue sample, and wherein the processor is configured to detect the presence of at least one of: a cancerous tissue and a necrotic tissue in the tissue sample. 
     
     
       5. The device of  claim 1 , wherein the target is a tissue, and wherein the identified oxygenation corresponds to tissue oxygenation. 
     
     
       6. The device of  claim 5 , wherein the tissue oxygenation comprises total hemoglobin content, oxy-hemoglobin content, de-oxy hemoglobin content, oxygen saturation, blood perfusion, or any combination thereof. 
     
     
       7. The device of  claim 1 , wherein the analysis model comprises an Artificial Neural Network (ANN) model, a Machine Learning model (ML), or a combination thereof. 
     
     
       8. The device of  claim 1 , wherein the target is a wound region, wherein the problematic cellular entity is a pathogen, and wherein when using the analysis model, the processor is configured to:
 identify a location of the wound region based on the fluorescence-based image; 
 detect presence of the pathogen in the wound region; and 
 classify the pathogen present in the wound region. 
 
     
     
       9. The device of  claim 1 , wherein the problematic cellular entity is a pathogen, wherein the processor is configured to determine at least one of: gram type, family, genus, species, and strain of the pathogen in the target based on the analysis of the first image. 
     
     
       10. The device of  claim 1 , wherein:
 the second light source is configured to illuminate the target with white light; 
 the image sensor is configured to:
 directly receive light emitted by the target in response to the illumination thereof by the second light source, and 
 capture a white-light image based on the received light, and 
 
 the processor is configured to detect the presence of an anomaly in the target based on analysis of the white-light image. 
 
     
     
       11. The device of  claim 1 , further comprising:
 a thermal sensor for thermal imaging of the problematic cellular entity. 
 
     
     
       12. The device of  claim 1 , wherein the image sensor is a charge coupled device (CCD) sensor, a CCD digital camera, a complementary metal-oxide semiconductor (CMOS) sensor, a CMOS digital camera, a single-photon avalanche diode (SPAD), an Avalanche Photodetector (APD) array, a photomultiplier tube (PMT) array, a Near-infrared (NIR) sensor, a Red Green Blue (RGB) sensor, or a combination thereof. 
     
     
       13. The device of  claim 1 , wherein the first light source is configured to emit the light with a wavelength in an ultraviolet (UV) region or a visible region, and the second light source is configured to emit the light with a wavelength in a Near Infra-Red (NIR) region or a visible region. 
     
     
       14. The device of  claim 1 , wherein the first light source is configured to emit light with a wavelength band of 200 nm-300 nm, 300 nm-400 nm, 400 nm-500 nm, or 500 nm-600 nm, and the second light source is configured to emit light with a wavelength band of 600 nm-700 nm, 700 nm-800 nm, or 800 nm-1000 nm. 
     
     
       15. The device of  claim 1  comprising:
 a first polarizer integrated with the first light source to let light waves of a specific polarization to pass through; 
 a second polarizer integrated with the image sensor to let light waves of a specific polarization to pass through; and 
 a third polarizer integrated with the second light source to let light wave of a specific polarization to pass through. 
 
     
     
       16. The device of  claim 1 , comprising a display configured to display a result of the detection of the problematic cellular entity, wherein the result is overlaid on an image of the target. 
     
     
       17. A system for examining a target, the system comprising:
 a processor to:
 receive a plurality of images of the target from a device that is coupled to the system, wherein the device comprises: 
 a first light source for emitting light for illuminating the target that causes a marker in the target to fluoresce, 
 a second light source for emitting light for illuminating the target without causing the marker in the target to fluoresce; 
 an image sensor configured to directly receive light emitted by the target in response to the illumination thereof by the first light source and by the second light source without an optical bandpass filter being disposed between the image sensor and the target, and to capture a plurality of images formed based on the light emitted; and 
 analyze, using an analysis model, a first image of the captured plurality of images, wherein the first image is a fluorescence-based image showing fluorescence emerging from the target; 
 analyze, using the analysis model, a second image of the captured plurality of images to identify oxygenation at a plurality of regions of the target; 
 detect, using the analysis model, presence of a problematic cellular entity in the target based on the analysis of the first image and based on the identified oxygenation at the plurality of regions of the target, wherein the analysis model is trained for detecting the presence of problematic cellular entities in targets by differentiating fluorescence, wherein the analysis model is trained using a plurality of reference fluorescence-based images to differentiate between fluorescence in the fluorescence-based image emerging from the problematic cellular entity and fluorescence in fluorescence-based image emerging from regions other than the problematic cellular entity; and 
 transmit, to the device, a result of the analysis, the result indicating whether the problematic cellular entity is present in the target. 
 
 
     
     
       18. The system of  claim 17 , comprising the device, wherein the device comprises:
 a first polarizer integrated with the first light source to let light waves of a specific polarization pass through thereof; 
 and 
 a second polarizer integrated with the image sensor to let light waves of a specific polarization to pass through thereof. 
 
     
     
       19. The system of  claim 18 , comprising a third polarizer integrated with the second light source to let light wave of a specific polarization to pass through. 
     
     
       20. The system of  claim 18 , wherein the first polarizer and the second polarizer are arranged in a cross-polarizer geometry to minimize the interference of the emitted light from the light source with the light emitted by the target. 
     
     
       21. A method for examining a target, the method comprising:
 illuminating the target using a first light source of a device, wherein light emitted by the first light source has a wavelength band that causes a marker in the target to fluoresce; 
 illuminating the target using a second light source of the device, light emitted by the second light source being at a wavelength band without causing the marker in the target to fluoresce; 
 directly receiving, by an image sensor of the device, light emitted by the target in response to the illumination thereof by the first light source and the second light source without an optical bandpass filter being disposed between the image sensor and the target, wherein a plurality of images formed based on the light emitted by the target are captured; 
 analyzing, by a processor, a first image of the captured plurality of images using an analysis model, wherein the first image is a fluorescence-based image comprising fluorescence emerging from the target in response to light emitted by the first light source; 
 analyzing, by the processor, a second image of the captured plurality of images using the analysis model to identify oxygenation at a plurality of regions of the target; and 
 detecting, by the processor, presence of a problematic cellular entity in the target using the analysis model based on the analysis of the first image and based on the identified oxygenation at the plurality of regions of the target, wherein the analysis model is trained for detecting the presence of problematic cellular entities in targets, wherein the analysis model is trained using a plurality of reference fluorescence-based images to differentiate between fluorescence in the fluorescence-based image emerging from the problematic cellular entity and fluorescence in fluorescence-based image emerging from regions of other than the problematic cellular entity. 
 
     
     
       22. The method of  claim 21 , wherein the target is one of a tissue, a tissue sample, or a wound, wherein the problematic cellular entity is a pathogen, and wherein the method comprises:
 identifying, by the processor, using the analysis model, location of the target in the fluorescence-based image; 
 detecting, by the processor, using the analysis model, presence of the pathogen in the target; and 
 classifying, by the processor, using the analysis model, the pathogen present in the target. 
 
     
     
       23. The method of  claim 21 , wherein:
 the target is a tissue sample or a tissue, and 
 the oxygenation corresponds to a tissue oxygenation, wherein the tissue oxygenation comprises total hemoglobin content, oxy-hemoglobin content, de-oxy-hemoglobin content, oxygen saturation, blood perfusion, or combinations thereof. 
 
     
     
       24. The method of  claim 21 , wherein the problematic cellular entity is a pathogen, wherein the method comprises:
 determining, by the processor, at least one of: a gram type, a family, a genus, a species, or a strain of the pathogen in the target based on the analysis of the first image. 
 
     
     
       25. The method of  claim 21 , comprising:
 illuminating, by the second light source of the device, the target with white light; 
 capturing, by the image sensor, a white-light image based on the received light; and 
 detecting, by the processor, the presence of an anomaly in the target based on analysis of the white-light image. 
 
     
     
       26. The method of  claim 21 , comprising:
 letting, by a first polarizer of the device integrated with the first light source, light waves of a specific polarization pass through; 
 letting, by a second polarizer of the device integrated with the image sensor, light waves of a specific polarization to pass through; and 
 letting, by a third polarizer of the device integrated with the second light source, light waves of a specific polarization to pass through.